xfs: generalize the freespace and reserved blocks handling

Christoph Hellwig · Christoph Hellwig · commit 712bae966318 · 2025-03-03T08:16:37.000-07:00
xfs_{add,dec}_freecounter already handles the block and RT extent
percpu counters, but it currently hardcodes the passed in counter.

Add a freecounter abstraction that uses an enum to designate the counter
and add wrappers that hide the actual percpu_counters.  This will allow
expanding the reserved block handling to the RT extent counter in the
next step, and also prepares for adding yet another such counter that
can share the code.  Both these additions will be needed for the zoned
allocator.

Also switch the flooring of the frextents counter to 0 in statfs for the
rthinherit case to a manual min_t call to match the handling of the
fdblocks counter for normal file systems.

Signed-off-by: Christoph Hellwig &lt;hch@lst.de&gt;
Reviewed-by: "Darrick J. Wong" &lt;djwong@kernel.org&gt;
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1927,7 +1927,7 @@ xfs_dialloc(
 	 * that we can immediately allocate, but then we allow allocation on the
 	 * second pass if we fail to find an AG with free inodes in it.
 	 */
-	if (percpu_counter_read_positive(&mp->m_fdblocks) <
+	if (xfs_estimate_freecounter(mp, XC_FREE_BLOCKS) <
 			mp->m_low_space[XFS_LOWSP_1_PCNT]) {
 		ok_alloc = false;
 		low_space = true;
diff --git a/fs/xfs/libxfs/xfs_metafile.c b/fs/xfs/libxfs/xfs_metafile.c
@@ -95,7 +95,7 @@ xfs_metafile_resv_can_cover(
 	 * There aren't enough blocks left in the inode's reservation, but it
 	 * isn't critical unless there also isn't enough free space.
 	 */
-	return __percpu_counter_compare(&ip->i_mount->m_fdblocks,
+	return xfs_compare_freecounter(ip->i_mount, XC_FREE_BLOCKS,
 			rhs - ip->i_delayed_blks, 2048) >= 0;
 }
 
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
@@ -1265,8 +1265,7 @@ xfs_log_sb(
 		mp->m_sb.sb_ifree = min_t(uint64_t,
 				percpu_counter_sum_positive(&mp->m_ifree),
 				mp->m_sb.sb_icount);
-		mp->m_sb.sb_fdblocks =
-				percpu_counter_sum_positive(&mp->m_fdblocks);
+		mp->m_sb.sb_fdblocks = xfs_sum_freecounter(mp, XC_FREE_BLOCKS);
 	}
 
 	/*
@@ -1275,9 +1274,10 @@ xfs_log_sb(
 	 * we handle nearly-lockless reservations, so we must use the _positive
 	 * variant here to avoid writing out nonsense frextents.
 	 */
-	if (xfs_has_rtgroups(mp))
+	if (xfs_has_rtgroups(mp)) {
 		mp->m_sb.sb_frextents =
-				percpu_counter_sum_positive(&mp->m_frextents);
+				xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS);
+	}
 
 	xfs_sb_to_disk(bp->b_addr, &mp->m_sb);
 	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
@@ -233,6 +233,23 @@ enum xfs_group_type {
 	{ XG_TYPE_AG,	"ag" }, \
 	{ XG_TYPE_RTG,	"rtg" }
 
+enum xfs_free_counter {
+	/*
+	 * Number of free blocks on the data device.
+	 */
+	XC_FREE_BLOCKS,
+
+	/*
+	 * Number of free RT extents on the RT device.
+	 */
+	XC_FREE_RTEXTENTS,
+	XC_FREE_NR,
+};
+
+#define XFS_FREECOUNTER_STR \
+	{ XC_FREE_BLOCKS,		"blocks" }, \
+	{ XC_FREE_RTEXTENTS,		"rtextents" }
+
 /*
  * Type verifier functions
  */
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
@@ -513,8 +513,8 @@ xchk_fscounters(
 	/* Snapshot the percpu counters. */
 	icount = percpu_counter_sum(&mp->m_icount);
 	ifree = percpu_counter_sum(&mp->m_ifree);
-	fdblocks = percpu_counter_sum(&mp->m_fdblocks);
-	frextents = percpu_counter_sum(&mp->m_frextents);
+	fdblocks = xfs_sum_freecounter_raw(mp, XC_FREE_BLOCKS);
+	frextents = xfs_sum_freecounter_raw(mp, XC_FREE_RTEXTENTS);
 
 	/* No negative values, please! */
 	if (icount < 0 || ifree < 0)
@@ -589,15 +589,16 @@ xchk_fscounters(
 			try_again = true;
 	}
 
-	if (!xchk_fscount_within_range(sc, fdblocks, &mp->m_fdblocks,
-			fsc->fdblocks)) {
+	if (!xchk_fscount_within_range(sc, fdblocks,
+			&mp->m_free[XC_FREE_BLOCKS].count, fsc->fdblocks)) {
 		if (fsc->frozen)
 			xchk_set_corrupt(sc);
 		else
 			try_again = true;
 	}
 
-	if (!xchk_fscount_within_range(sc, frextents, &mp->m_frextents,
+	if (!xchk_fscount_within_range(sc, frextents,
+			&mp->m_free[XC_FREE_RTEXTENTS].count,
 			fsc->frextents - fsc->frextents_delayed)) {
 		if (fsc->frozen)
 			xchk_set_corrupt(sc);
diff --git a/fs/xfs/scrub/fscounters_repair.c b/fs/xfs/scrub/fscounters_repair.c
@@ -64,7 +64,7 @@ xrep_fscounters(
 
 	percpu_counter_set(&mp->m_icount, fsc->icount);
 	percpu_counter_set(&mp->m_ifree, fsc->ifree);
-	percpu_counter_set(&mp->m_fdblocks, fsc->fdblocks);
+	xfs_set_freecounter(mp, XC_FREE_BLOCKS, fsc->fdblocks);
 
 	/*
 	 * Online repair is only supported on v5 file systems, which require
@@ -74,7 +74,7 @@ xrep_fscounters(
 	 * track of the delalloc reservations separately, as they are are
 	 * subtracted from m_frextents, but not included in sb_frextents.
 	 */
-	percpu_counter_set(&mp->m_frextents,
+	xfs_set_freecounter(mp, XC_FREE_RTEXTENTS,
 		fsc->frextents - fsc->frextents_delayed);
 	if (!xfs_has_rtgroups(mp))
 		mp->m_sb.sb_frextents = fsc->frextents;
diff --git a/fs/xfs/scrub/newbt.c b/fs/xfs/scrub/newbt.c
@@ -62,7 +62,7 @@ xrep_newbt_estimate_slack(
 		free = sc->sa.pag->pagf_freeblks;
 		sz = xfs_ag_block_count(sc->mp, pag_agno(sc->sa.pag));
 	} else {
-		free = percpu_counter_sum(&sc->mp->m_fdblocks);
+		free = xfs_sum_freecounter_raw(sc->mp, XC_FREE_BLOCKS);
 		sz = sc->mp->m_sb.sb_dblocks;
 	}
 
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
@@ -409,7 +409,7 @@ xfs_reserve_blocks(
 
 	/*
 	 * If the request is larger than the current reservation, reserve the
-	 * blocks before we update the reserve counters. Sample m_fdblocks and
+	 * blocks before we update the reserve counters. Sample m_free and
 	 * perform a partial reservation if the request exceeds free space.
 	 *
 	 * The code below estimates how many blocks it can request from
@@ -419,8 +419,8 @@ xfs_reserve_blocks(
 	 * space to fill it because mod_fdblocks will refill an undersized
 	 * reserve when it can.
 	 */
-	free = percpu_counter_sum(&mp->m_fdblocks) -
-						xfs_fdblocks_unavailable(mp);
+	free = xfs_sum_freecounter_raw(mp, XC_FREE_BLOCKS) -
+		xfs_freecounter_unavailable(mp, XC_FREE_BLOCKS);
 	delta = request - mp->m_resblks;
 	mp->m_resblks = request;
 	if (delta > 0 && free > 0) {
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
@@ -2076,7 +2076,7 @@ xfs_inodegc_want_queue_rt_file(
 	if (!XFS_IS_REALTIME_INODE(ip))
 		return false;
 
-	if (__percpu_counter_compare(&mp->m_frextents,
+	if (xfs_compare_freecounter(mp, XC_FREE_RTEXTENTS,
 				mp->m_low_rtexts[XFS_LOWSP_5_PCNT],
 				XFS_FDBLOCKS_BATCH) < 0)
 		return true;
@@ -2104,7 +2104,7 @@ xfs_inodegc_want_queue_work(
 	if (items > mp->m_ino_geo.inodes_per_cluster)
 		return true;
 
-	if (__percpu_counter_compare(&mp->m_fdblocks,
+	if (xfs_compare_freecounter(mp, XC_FREE_BLOCKS,
 				mp->m_low_space[XFS_LOWSP_5_PCNT],
 				XFS_FDBLOCKS_BATCH) < 0)
 		return true;
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
@@ -1155,9 +1155,9 @@ xfs_ioctl_fs_counts(
 	struct xfs_fsop_counts	out = {
 		.allocino = percpu_counter_read_positive(&mp->m_icount),
 		.freeino  = percpu_counter_read_positive(&mp->m_ifree),
-		.freedata = percpu_counter_read_positive(&mp->m_fdblocks) -
-				xfs_fdblocks_unavailable(mp),
-		.freertx  = percpu_counter_read_positive(&mp->m_frextents),
+		.freedata = xfs_estimate_freecounter(mp, XC_FREE_BLOCKS) -
+				xfs_freecounter_unavailable(mp, XC_FREE_BLOCKS),
+		.freertx  = xfs_estimate_freecounter(mp, XC_FREE_RTEXTENTS),
 	};
 
 	if (copy_to_user(uarg, &out, sizeof(out)))
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
@@ -431,13 +431,14 @@ xfs_quota_calc_throttle(
 
 static int64_t
 xfs_iomap_freesp(
-	struct percpu_counter	*counter,
+	struct xfs_mount	*mp,
+	unsigned int		idx,
 	uint64_t		low_space[XFS_LOWSP_MAX],
 	int			*shift)
 {
 	int64_t			freesp;
 
-	freesp = percpu_counter_read_positive(counter);
+	freesp = xfs_estimate_freecounter(mp, idx);
 	if (freesp < low_space[XFS_LOWSP_5_PCNT]) {
 		*shift = 2;
 		if (freesp < low_space[XFS_LOWSP_4_PCNT])
@@ -536,10 +537,10 @@ xfs_iomap_prealloc_size(
 
 	if (unlikely(XFS_IS_REALTIME_INODE(ip)))
 		freesp = xfs_rtbxlen_to_blen(mp,
-				xfs_iomap_freesp(&mp->m_frextents,
+				xfs_iomap_freesp(mp, XC_FREE_RTEXTENTS,
 					mp->m_low_rtexts, &shift));
 	else
-		freesp = xfs_iomap_freesp(&mp->m_fdblocks, mp->m_low_space,
+		freesp = xfs_iomap_freesp(mp, XC_FREE_BLOCKS, mp->m_low_space,
 				&shift);
 
 	/*
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
@@ -1220,21 +1220,39 @@ xfs_fs_writable(
 	return true;
 }
 
+/*
+ * Estimate the amount of free space that is not available to userspace and is
+ * not explicitly reserved from the incore fdblocks.  This includes:
+ *
+ * - The minimum number of blocks needed to support splitting a bmap btree
+ * - The blocks currently in use by the freespace btrees because they record
+ *   the actual blocks that will fill per-AG metadata space reservations
+ */
+uint64_t
+xfs_freecounter_unavailable(
+	struct xfs_mount	*mp,
+	enum xfs_free_counter	ctr)
+{
+	if (ctr != XC_FREE_BLOCKS)
+		return 0;
+	return mp->m_alloc_set_aside + atomic64_read(&mp->m_allocbt_blks);
+}
+
 void
 xfs_add_freecounter(
 	struct xfs_mount	*mp,
-	struct percpu_counter	*counter,
+	enum xfs_free_counter	ctr,
 	uint64_t		delta)
 {
-	bool			has_resv_pool = (counter == &mp->m_fdblocks);
+	bool			has_resv_pool = (ctr == XC_FREE_BLOCKS);
 	uint64_t		res_used;
 
 	/*
 	 * If the reserve pool is depleted, put blocks back into it first.
 	 * Most of the time the pool is full.
 	 */
 	if (!has_resv_pool || mp->m_resblks == mp->m_resblks_avail) {
-		percpu_counter_add(counter, delta);
+		percpu_counter_add(&mp->m_free[ctr].count, delta);
 		return;
 	}
 
@@ -1245,24 +1263,27 @@ xfs_add_freecounter(
 	} else {
 		delta -= res_used;
 		mp->m_resblks_avail = mp->m_resblks;
-		percpu_counter_add(counter, delta);
+		percpu_counter_add(&mp->m_free[ctr].count, delta);
 	}
 	spin_unlock(&mp->m_sb_lock);
 }
 
+
+/* Adjust in-core free blocks or RT extents. */
 int
 xfs_dec_freecounter(
 	struct xfs_mount	*mp,
-	struct percpu_counter	*counter,
+	enum xfs_free_counter	ctr,
 	uint64_t		delta,
 	bool			rsvd)
 {
+	struct percpu_counter	*counter = &mp->m_free[ctr].count;
 	uint64_t		set_aside = 0;
 	s32			batch;
 	bool			has_resv_pool;
 
-	ASSERT(counter == &mp->m_fdblocks || counter == &mp->m_frextents);
-	has_resv_pool = (counter == &mp->m_fdblocks);
+	ASSERT(ctr < XC_FREE_NR);
+	has_resv_pool = (ctr == XC_FREE_BLOCKS);
 	if (rsvd)
 		ASSERT(has_resv_pool);
 
@@ -1292,7 +1313,7 @@ xfs_dec_freecounter(
 	 * slightly premature -ENOSPC.
 	 */
 	if (has_resv_pool)
-		set_aside = xfs_fdblocks_unavailable(mp);
+		set_aside = xfs_freecounter_unavailable(mp, ctr);
 	percpu_counter_add_batch(counter, -((int64_t)delta), batch);
 	if (__percpu_counter_compare(counter, set_aside,
 			XFS_FDBLOCKS_BATCH) < 0) {
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h

Original file line number	Diff line number	Diff line change
`@@ -95,7 +95,7 @@ xfs_metafile_resv_can_cover(`
`95`	`95`	`* There aren't enough blocks left in the inode's reservation, but it`
`96`	`96`	`* isn't critical unless there also isn't enough free space.`
`97`	`97`	`*/`
`98`		`- return __percpu_counter_compare(&ip->i_mount->m_fdblocks,`
	`98`	`+ return xfs_compare_freecounter(ip->i_mount, XC_FREE_BLOCKS,`
`99`	`99`	`rhs - ip->i_delayed_blks, 2048) >= 0;`
`100`	`100`	`}`
`101`	`101`
Original file line number	Diff line number	Diff line change
`@@ -62,7 +62,7 @@ xrep_newbt_estimate_slack(`
`62`	`62`	`free = sc->sa.pag->pagf_freeblks;`
`63`	`63`	`sz = xfs_ag_block_count(sc->mp, pag_agno(sc->sa.pag));`
`64`	`64`	`} else {`
`65`		`- free = percpu_counter_sum(&sc->mp->m_fdblocks);`
	`65`	`+ free = xfs_sum_freecounter_raw(sc->mp, XC_FREE_BLOCKS);`
`66`	`66`	`sz = sc->mp->m_sb.sb_dblocks;`
`67`	`67`	`}`
`68`	`68`